Hugging Face's logo

Cristhian2430
/
whisper-large-coes-v3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Spanish
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-large-coes-v3 / README.md
Cristhian2430's picture
Cristhian2430
End of training
3c8ffe8
preview code
|
raw
history blame contribute delete
1.73 kB
metadata
language:
  - es
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Large SEIN - COES SEIN - Version 3
    results: []

Whisper Large SEIN - COES SEIN - Version 3

This model is a fine-tuned version of openai/whisper-large-v3 on the SEIN COES dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0000
  • Wer: 44.0630

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0002 142.86 1000 0.0002 36.1325
0.0001 285.71 2000 0.0001 40.0109
0.0 428.57 3000 0.0000 43.4981
0.0 571.43 4000 0.0000 44.0630

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0